Feature-Based Image Mosaicing

Part of the Springer Tracts in Advanced Robotics book series (STAR, volume 82)

Abstract

FIM can be divided into two main steps: image spatial alignment, also known in the literature as image registration or motion estimation, and image intensity blending for rendering the final mosaic. The spatial alignment step can be further divided into pairwise and global alignments. Pairwise alignment is used to find the motion between two overlapping images; images have to be mapped onto a common frame, also known as the global frame, in order to obtain globally coherent mosaics. Global alignment refers to as the problem of finding the image registration parameters that best comply with the constraints introduced by the image matching. Global alignment methods are used to compensate for the errors in pairwise registration.

Although the alignment between images may be close to perfect, intensity differences do not allow the creation of a seamless mosaic. Image blending methods are needed to deal with the problem of intensity differences between images after they have been aligned. Several methods have been proposed for image blending [23, 68, 99, 127] as well as for mosaicing [116]. Pairwise and global alignment methods are reviewed and detailed later in this chapter.

Keywords

Singular Value Decomposition Global Alignment Bundle Adjustment Global Frame Euclidean Transformation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Department of Mathematical EngineeringYildiz Technical UniversityIstanbulTurkey
  2. 2.Computer Vision and Robotics GroupUniversity of GironaGironaSpain

Personalised recommendations